experiential tested by Argusic Runner

What the test found

The experiential project installs cleanly under uv on Python 3.13 with the native Rust gateway extension built from source; all quality gates pass, 8396 of 8397 container-runnable tests pass, and the initialized loopback gateway serves health, models, non-stream and stream chat completions, and usage accounting against a local mock OpenAI-compatible upstream.

Full pytest: 8396 passed, 1 failed (macOS-only capture lock env test), 1 flaky error passing in isolation, 60 skipped in 26.4 min. ruff check, ruff format --check, ty check all pass. Live gateway verified end to end with a schema-correct local mock OpenAI upstream: health 200, /v1/models 200, non-stream and stream chat completions 200 with real content, /usage HTML accounting 200, SQLite WAL traffic written. No repo files modified; rustc/uv/python3.13 installed user-local.

Argusic installed experiential in 45 minutes and launched it; verification reached Verified running for real. 7 of 7 recorded errors were worked through (see the timeline below).

Runsall runs of experiential

This summary is drawn from the agent's recorded report for this run. Every figure traces to the log and recording above; nothing here is authored.